Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 60938
    Prev
    Next
    INDEX
    Explanations

    the presence of conditional statements in code, specifically the "else" clause

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    else
    -1.45
    elif
    -1.02
     else
    -1.02
    otherwise
    -0.86
     altro
    -0.80
    Elsewhere
    -0.78
     sonst
    -0.78
     ailleurs
    -0.76
     other
    -0.74
    Otherwise
    -0.73
    POSITIVE LOGITS
    SequentialGroup
    0.79
    Geplaatst
    0.74
    VersionUID
    0.73
     cherchés
    0.71
    BufferException
    0.69
    Sucesor
    0.68
    帖最后由
    0.67
     AssemblyProduct
    0.65
    ImageContext
    0.64
     виправивши
    0.64
    Activations Density 0.012%

    No Known Activations